update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,119 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- hyperpartisan_news_detection
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
model-index:
|
10 |
+
- name: hyperpartisan-classifier
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Text Classification
|
14 |
+
type: text-classification
|
15 |
+
dataset:
|
16 |
+
name: hyperpartisan_news_detection
|
17 |
+
type: hyperpartisan_news_detection
|
18 |
+
config: bypublisher
|
19 |
+
split: validation
|
20 |
+
args: bypublisher
|
21 |
+
metrics:
|
22 |
+
- name: Accuracy
|
23 |
+
type: accuracy
|
24 |
+
value: 0.9988466666666667
|
25 |
+
---
|
26 |
+
|
27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
28 |
+
should probably proofread and complete it, then remove this comment. -->
|
29 |
+
|
30 |
+
# hyperpartisan-classifier
|
31 |
+
|
32 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the hyperpartisan_news_detection dataset.
|
33 |
+
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 0.0036
|
35 |
+
- Accuracy: 0.9988
|
36 |
+
|
37 |
+
## Model description
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Intended uses & limitations
|
42 |
+
|
43 |
+
More information needed
|
44 |
+
|
45 |
+
## Training and evaluation data
|
46 |
+
|
47 |
+
More information needed
|
48 |
+
|
49 |
+
## Training procedure
|
50 |
+
|
51 |
+
### Training hyperparameters
|
52 |
+
|
53 |
+
The following hyperparameters were used during training:
|
54 |
+
- learning_rate: 2e-05
|
55 |
+
- train_batch_size: 64
|
56 |
+
- eval_batch_size: 64
|
57 |
+
- seed: 42
|
58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
+
- lr_scheduler_type: linear
|
60 |
+
- num_epochs: 5
|
61 |
+
|
62 |
+
### Training results
|
63 |
+
|
64 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
65 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
66 |
+
| 0.1441 | 0.11 | 1000 | 0.1391 | 0.9453 |
|
67 |
+
| 0.1248 | 0.21 | 2000 | 0.1042 | 0.9595 |
|
68 |
+
| 0.1027 | 0.32 | 3000 | 0.0913 | 0.9647 |
|
69 |
+
| 0.0928 | 0.43 | 4000 | 0.0827 | 0.9688 |
|
70 |
+
| 0.0992 | 0.53 | 5000 | 0.0799 | 0.9698 |
|
71 |
+
| 0.0881 | 0.64 | 6000 | 0.0710 | 0.9741 |
|
72 |
+
| 0.078 | 0.75 | 7000 | 0.0640 | 0.9762 |
|
73 |
+
| 0.0708 | 0.85 | 8000 | 0.0626 | 0.9764 |
|
74 |
+
| 0.0696 | 0.96 | 9000 | 0.0564 | 0.9792 |
|
75 |
+
| 0.0586 | 1.07 | 10000 | 0.0516 | 0.9813 |
|
76 |
+
| 0.0558 | 1.17 | 11000 | 0.0507 | 0.9815 |
|
77 |
+
| 0.0531 | 1.28 | 12000 | 0.0463 | 0.9829 |
|
78 |
+
| 0.0585 | 1.39 | 13000 | 0.0468 | 0.9831 |
|
79 |
+
| 0.0488 | 1.49 | 14000 | 0.0403 | 0.9854 |
|
80 |
+
| 0.057 | 1.6 | 15000 | 0.0393 | 0.9865 |
|
81 |
+
| 0.0514 | 1.71 | 16000 | 0.0349 | 0.9879 |
|
82 |
+
| 0.052 | 1.81 | 17000 | 0.0366 | 0.9868 |
|
83 |
+
| 0.0572 | 1.92 | 18000 | 0.0300 | 0.9895 |
|
84 |
+
| 0.0311 | 2.03 | 19000 | 0.0309 | 0.9893 |
|
85 |
+
| 0.0332 | 2.13 | 20000 | 0.0262 | 0.9908 |
|
86 |
+
| 0.0396 | 2.24 | 21000 | 0.0250 | 0.9914 |
|
87 |
+
| 0.0314 | 2.35 | 22000 | 0.0223 | 0.9924 |
|
88 |
+
| 0.0361 | 2.45 | 23000 | 0.0236 | 0.9919 |
|
89 |
+
| 0.0289 | 2.56 | 24000 | 0.0197 | 0.9933 |
|
90 |
+
| 0.0322 | 2.67 | 25000 | 0.0182 | 0.9939 |
|
91 |
+
| 0.0416 | 2.77 | 26000 | 0.0183 | 0.9937 |
|
92 |
+
| 0.0273 | 2.88 | 27000 | 0.0159 | 0.9946 |
|
93 |
+
| 0.0317 | 2.99 | 28000 | 0.0152 | 0.9949 |
|
94 |
+
| 0.0203 | 3.09 | 29000 | 0.0132 | 0.9957 |
|
95 |
+
| 0.0182 | 3.2 | 30000 | 0.0146 | 0.9953 |
|
96 |
+
| 0.0165 | 3.31 | 31000 | 0.0123 | 0.9961 |
|
97 |
+
| 0.0184 | 3.41 | 32000 | 0.0105 | 0.9968 |
|
98 |
+
| 0.0208 | 3.52 | 33000 | 0.0103 | 0.9967 |
|
99 |
+
| 0.0187 | 3.63 | 34000 | 0.0083 | 0.9973 |
|
100 |
+
| 0.0183 | 3.73 | 35000 | 0.0076 | 0.9977 |
|
101 |
+
| 0.0258 | 3.84 | 36000 | 0.0073 | 0.9977 |
|
102 |
+
| 0.0114 | 3.95 | 37000 | 0.0066 | 0.9979 |
|
103 |
+
| 0.007 | 4.05 | 38000 | 0.0052 | 0.9983 |
|
104 |
+
| 0.0094 | 4.16 | 39000 | 0.0061 | 0.9981 |
|
105 |
+
| 0.0106 | 4.27 | 40000 | 0.0053 | 0.9983 |
|
106 |
+
| 0.0134 | 4.37 | 41000 | 0.0052 | 0.9984 |
|
107 |
+
| 0.0087 | 4.48 | 42000 | 0.0040 | 0.9987 |
|
108 |
+
| 0.018 | 4.59 | 43000 | 0.0047 | 0.9985 |
|
109 |
+
| 0.0118 | 4.69 | 44000 | 0.0041 | 0.9987 |
|
110 |
+
| 0.012 | 4.8 | 45000 | 0.0038 | 0.9988 |
|
111 |
+
| 0.0165 | 4.91 | 46000 | 0.0036 | 0.9988 |
|
112 |
+
|
113 |
+
|
114 |
+
### Framework versions
|
115 |
+
|
116 |
+
- Transformers 4.27.0.dev0
|
117 |
+
- Pytorch 1.13.1+cu116
|
118 |
+
- Datasets 2.9.0
|
119 |
+
- Tokenizers 0.13.2
|